{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/adam/papers/205","list_of":"/method/adam","method":"Adam","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":205,"pages_in_order":244,"rows_per_page":100,"rows":[20401,20500],"of":24390,"counts":{"archive_papers_tagged":24390,"with_a_code_link":10944,"where_syntology_ran_a_sample":3424,"not_listed_spam_title":0,"listed":24390,"listed_where_code_ran":3424,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2899,"every_run_a_failure_of_syntologys_instrument":525,"listed_with_a_run_with_no_instrument_failure":2899,"listed_every_run_a_failure_of_syntologys_instrument":525,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/adam","prev":"/method/adam/papers/204","next":"/method/adam/papers/206","papers":[{"paper":"/paper/automatic-punctuation-restoration-with-bert","slug":"automatic-punctuation-restoration-with-bert","title":"Automatic punctuation restoration with BERT models","date":"2021-01-18","arxiv_id":"2101.07343","n_code_links":1,"syntology":null},{"paper":"/paper/can-a-fruit-fly-learn-word-embeddings-1","slug":"can-a-fruit-fly-learn-word-embeddings-1","title":"Can a Fruit Fly Learn Word Embeddings?","date":"2021-01-18","arxiv_id":"2101.06887","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/inference-for-bart-with-multinomial-outcomes","slug":"inference-for-bart-with-multinomial-outcomes","title":"Inference for BART with Multinomial Outcomes","date":"2021-01-18","arxiv_id":"2101.06823","n_code_links":1,"syntology":null},{"paper":"/paper/dual-level-collaborative-transformer-for","slug":"dual-level-collaborative-transformer-for","title":"Dual-Level Collaborative Transformer for Image Captioning","date":"2021-01-16","arxiv_id":"2101.06462","n_code_links":1,"syntology":null},{"paper":"/paper/match-ignition-plugging-pagerank-into","slug":"match-ignition-plugging-pagerank-into","title":"Match-Ignition: Plugging PageRank into Transformer for Long-form Text Matching","date":"2021-01-16","arxiv_id":"2101.06423","n_code_links":1,"syntology":null},{"paper":null,"slug":"transformer-based-models-for-question","title":"Transformer-Based Models for Question Answering on COVID19","date":"2021-01-16","arxiv_id":"2101.11432","n_code_links":0,"syntology":null},{"paper":null,"slug":"grid-search-hyperparameter-benchmarking-of","title":"Grid Search Hyperparameter Benchmarking of BERT, ALBERT, and LongFormer on DuoRC","date":"2021-01-15","arxiv_id":"2101.06326","n_code_links":0,"syntology":null},{"paper":null,"slug":"hostility-detection-and-covid-19-fake-news","title":"Hostility Detection and Covid-19 Fake News Detection in Social Media","date":"2021-01-15","arxiv_id":"2101.05953","n_code_links":0,"syntology":null},{"paper":null,"slug":"kdlsq-bert-a-quantized-bert-combining","title":"KDLSQ-BERT: A Quantized Bert Combining Knowledge Distillation with Learned Step Size Quantization","date":"2021-01-15","arxiv_id":"2101.05938","n_code_links":0,"syntology":null},{"paper":"/paper/ecol-early-detection-of-covid-lies-using","slug":"ecol-early-detection-of-covid-lies-using","title":"ECOL: Early Detection of COVID Lies Using Content, Prior Knowledge and Source Information","date":"2021-01-14","arxiv_id":"2101.05499","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploration-of-visual-features-and-their","title":"Exploration of Visual Features and their weighted-additive fusion for Video Captioning","date":"2021-01-14","arxiv_id":"2101.05806","n_code_links":0,"syntology":null},{"paper":"/paper/gan-inversion-a-survey","slug":"gan-inversion-a-survey","title":"GAN Inversion: A Survey","date":"2021-01-14","arxiv_id":"2101.05278","n_code_links":1,"syntology":null},{"paper":"/paper/persistent-anti-muslim-bias-in-large-language","slug":"persistent-anti-muslim-bias-in-large-language","title":"Persistent Anti-Muslim Bias in Large Language Models","date":"2021-01-14","arxiv_id":"2101.05783","n_code_links":1,"syntology":null},{"paper":null,"slug":"privacy-analysis-in-language-models-via","title":"Training Data Leakage Analysis in Language Models","date":"2021-01-14","arxiv_id":"2101.05405","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-practical-adam-non-convexity","title":"Towards Practical Adam: Non-Convexity, Convergence Theory, and Mini-Batch Acceleration","date":"2021-01-14","arxiv_id":"2101.05471","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-based-language-model-fine-tuning","title":"Transformer-based Language Model Fine-tuning Methods for COVID-19 Fake News Detection","date":"2021-01-14","arxiv_id":"2101.05509","n_code_links":0,"syntology":null},{"paper":null,"slug":"wer-bert-automatic-wer-estimation-with-bert","title":"WER-BERT: Automatic WER Estimation with BERT in a Balanced Ordinal Classification Paradigm","date":"2021-01-14","arxiv_id":"2101.05478","n_code_links":0,"syntology":null},{"paper":"/paper/coarse-and-fine-grained-hostility-detection","slug":"coarse-and-fine-grained-hostility-detection","title":"Coarse and Fine-Grained Hostility Detection in Hindi Posts using Fine Tuned Multilingual Embeddings","date":"2021-01-13","arxiv_id":"2101.04998","n_code_links":1,"syntology":null},{"paper":null,"slug":"experimental-evaluation-of-deep-learning","title":"Experimental Evaluation of Deep Learning models for Marathi Text Classification","date":"2021-01-13","arxiv_id":"2101.04899","n_code_links":0,"syntology":null},{"paper":null,"slug":"heterogeneous-network-embedding-for-deep","title":"Heterogeneous Network Embedding for Deep Semantic Relevance Match in E-commerce Search","date":"2021-01-13","arxiv_id":"2101.04850","n_code_links":0,"syntology":null},{"paper":"/paper/ladiff-ulmfit-a-layer-differentiated-training","slug":"ladiff-ulmfit-a-layer-differentiated-training","title":"LaDiff ULMFiT: A Layer Differentiated training approach for ULMFiT","date":"2021-01-13","arxiv_id":"2101.04965","n_code_links":1,"syntology":null},{"paper":null,"slug":"fake-news-detection-system-using-xlnet-model","title":"Fake News Detection System using XLNet model with Topic Distributions: CONSTRAINT@AAAI2021 Shared Task","date":"2021-01-12","arxiv_id":"2101.11425","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-contract-element-extraction-revisited","title":"Neural Contract Element Extraction Revisited: Letters from Sesame Street","date":"2021-01-12","arxiv_id":"2101.04355","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-news-recommendation-with-negative","title":"Neural News Recommendation with Negative Feedback","date":"2021-01-12","arxiv_id":"2101.04328","n_code_links":0,"syntology":null},{"paper":"/paper/of-non-linearity-and-commutativity-in-bert","slug":"of-non-linearity-and-commutativity-in-bert","title":"Of Non-Linearity and Commutativity in BERT","date":"2021-01-12","arxiv_id":"2101.04547","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-more-efficient-chinese-named-entity","title":"A More Efficient Chinese Named Entity Recognition base on BERT and Syntactic Analysis","date":"2021-01-11","arxiv_id":"2101.11423","n_code_links":0,"syntology":null},{"paper":null,"slug":"at-bert-adversarial-training-bert-for-acronym","title":"AT-BERT: Adversarial Training BERT for Acronym Identification Winning Solution for SDU@AAAI-21","date":"2021-01-11","arxiv_id":"2101.03700","n_code_links":0,"syntology":null},{"paper":"/paper/bert-gt-cross-sentence-n-ary-relation","slug":"bert-gt-cross-sentence-n-ary-relation","title":"BERT-GT: Cross-sentence n-ary relation extraction with BERT and Graph Transformer","date":"2021-01-11","arxiv_id":"2101.04158","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluation-of-deep-learning-models-for","title":"Evaluation of Deep Learning Models for Hostility Detection in Hindi Text","date":"2021-01-11","arxiv_id":"2101.04144","n_code_links":0,"syntology":null},{"paper":null,"slug":"investigating-the-vision-transformer-model","title":"Investigating the Vision Transformer Model for Image Retrieval Tasks","date":"2021-01-11","arxiv_id":"2101.03771","n_code_links":0,"syntology":null},{"paper":"/paper/revisiting-mahalanobis-distance-for","slug":"revisiting-mahalanobis-distance-for","title":"Revisiting Mahalanobis Distance for Transformer-Based Out-of-Domain Detection","date":"2021-01-11","arxiv_id":"2101.03778","n_code_links":1,"syntology":null},{"paper":null,"slug":"spherical-transformer-adapting-spherical","title":"Spherical Transformer: Adapting Spherical Signal to CNNs","date":"2021-01-11","arxiv_id":"2101.03848","n_code_links":0,"syntology":null},{"paper":"/paper/bert-family-eat-word-salad-experiments-with","slug":"bert-family-eat-word-salad-experiments-with","title":"BERT & Family Eat Word Salad: Experiments with Text Understanding","date":"2021-01-10","arxiv_id":"2101.03453","n_code_links":1,"syntology":null},{"paper":null,"slug":"channel-boosting-feature-ensemble-for-radar","title":"Channel Boosting Feature Ensemble for Radar-based Object Detection","date":"2021-01-10","arxiv_id":"2101.03531","n_code_links":0,"syntology":null},{"paper":"/paper/cisco-at-aaai-cad21-shared-task-predicting","slug":"cisco-at-aaai-cad21-shared-task-predicting","title":"Cisco at AAAI-CAD21 shared task: Predicting Emphasis in Presentation Slides using Contextualized Embeddings","date":"2021-01-10","arxiv_id":"2101.11422","n_code_links":1,"syntology":null},{"paper":"/paper/deep-reinforcement-learning-with-function","slug":"deep-reinforcement-learning-with-function","title":"Deep Reinforcement Learning with Function Properties in Mean Reversion Strategies","date":"2021-01-09","arxiv_id":"2101.03418","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-better-sentence-representation-with","title":"Learning Better Sentence Representation with Syntax Information","date":"2021-01-09","arxiv_id":"2101.03343","n_code_links":0,"syntology":null},{"paper":"/paper/trankit-a-light-weight-transformer-based","slug":"trankit-a-light-weight-transformer-based","title":"Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processing","date":"2021-01-09","arxiv_id":"2101.03289","n_code_links":1,"syntology":null},{"paper":"/paper/contextual-non-local-alignment-over-full","slug":"contextual-non-local-alignment-over-full","title":"Contextual Non-Local Alignment over Full-Scale Representation for Text-Based Person Search","date":"2021-01-08","arxiv_id":"2101.03036","n_code_links":2,"syntology":null},{"paper":"/paper/leveraging-multilingual-transformers-for-hate","slug":"leveraging-multilingual-transformers-for-hate","title":"Leveraging Multilingual Transformers for Hate Speech Detection","date":"2021-01-08","arxiv_id":"2101.03207","n_code_links":1,"syntology":null},{"paper":null,"slug":"misspelling-correction-with-pre-trained","title":"Misspelling Correction with Pre-trained Contextual Language Model","date":"2021-01-08","arxiv_id":"2101.03204","n_code_links":0,"syntology":null},{"paper":null,"slug":"applying-transfer-learning-for-improving","title":"Applying Transfer Learning for Improving Domain-Specific Search Experience Using Query to Question Similarity","date":"2021-01-07","arxiv_id":"2101.02351","n_code_links":0,"syntology":null},{"paper":"/paper/compound-word-transformer-learning-to-compose","slug":"compound-word-transformer-learning-to-compose","title":"Compound Word Transformer: Learning to Compose Full-Song Music over Dynamic Directed Hypergraphs","date":"2021-01-07","arxiv_id":"2101.02402","n_code_links":5,"syntology":{"ran":4,"of":9,"n_ran_checked":4,"n_instrument":0,"unverified":5,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["YatingMusic/compound-word-transformer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/exploring-text-transformers-in-aaai-2021","slug":"exploring-text-transformers-in-aaai-2021","title":"Exploring Text-transformers in AAAI 2021 Shared Task: COVID-19 Fake News Detection in English","date":"2021-01-07","arxiv_id":"2101.02359","n_code_links":1,"syntology":null},{"paper":null,"slug":"homonym-identification-using-bert-using-a","title":"Homonym Identification using BERT -- Using a Clustering Approach","date":"2021-01-07","arxiv_id":"2101.02398","n_code_links":0,"syntology":null},{"paper":"/paper/trackformer-multi-object-tracking-with","slug":"trackformer-multi-object-tracking-with","title":"TrackFormer: Multi-Object Tracking with Transformers","date":"2021-01-07","arxiv_id":"2101.02702","n_code_links":2,"syntology":null},{"paper":"/paper/transformer-based-approach-towards-music","slug":"transformer-based-approach-towards-music","title":"Transformer-based approach towards music emotion recognition from lyrics","date":"2021-01-06","arxiv_id":"2101.02051","n_code_links":1,"syntology":null},{"paper":"/paper/autodropout-learning-dropout-patterns-to","slug":"autodropout-learning-dropout-patterns-to","title":"AutoDropout: Learning Dropout Patterns to Regularize Deep Networks","date":"2021-01-05","arxiv_id":"2101.01761","n_code_links":1,"syntology":null},{"paper":null,"slug":"covid-19-comparative-analysis-of-methods-for","title":"COVID-19: Comparative Analysis of Methods for Identifying Articles Related to Therapeutics and Vaccines without Using Labeled Data","date":"2021-01-05","arxiv_id":"2101.02017","n_code_links":0,"syntology":null},{"paper":"/paper/i-bert-integer-only-bert-quantization","slug":"i-bert-integer-only-bert-quantization","title":"I-BERT: Integer-only BERT Quantization","date":"2021-01-05","arxiv_id":"2101.01321","n_code_links":7,"syntology":null},{"paper":"/paper/generalized-latency-performance-estimation","slug":"generalized-latency-performance-estimation","title":"Generalized Latency Performance Estimation for Once-For-All Neural Architecture Search","date":"2021-01-04","arxiv_id":"2101.00732","n_code_links":2,"syntology":null},{"paper":"/paper/improving-reference-mining-in-patents-with","slug":"improving-reference-mining-in-patents-with","title":"Improving reference mining in patents with BERT","date":"2021-01-04","arxiv_id":"2101.01039","n_code_links":1,"syntology":null},{"paper":"/paper/transformers-and-transfer-learning-for","slug":"transformers-and-transfer-learning-for","title":"Improving Portuguese Semantic Role Labeling with Transformers and Transfer Learning","date":"2021-01-04","arxiv_id":"2101.01213","n_code_links":1,"syntology":null},{"paper":null,"slug":"transformers-in-vision-a-survey","title":"Transformers in Vision: A Survey","date":"2021-01-04","arxiv_id":"2101.01169","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-bart-for-multiobjective-optimization-of","title":"Using BART to Perform Pareto Optimization and Quantify its Uncertainties","date":"2021-01-04","arxiv_id":"2101.02558","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-efficient-transformer-decoder-with","title":"An Efficient Transformer Decoder with Compressed Sub-layers","date":"2021-01-03","arxiv_id":"2101.00542","n_code_links":0,"syntology":null},{"paper":"/paper/a-robust-and-domain-adaptive-approach-for-low","slug":"a-robust-and-domain-adaptive-approach-for-low","title":"A Robust and Domain-Adaptive Approach for Low-Resource Named Entity Recognition","date":"2021-01-02","arxiv_id":"2101.00388","n_code_links":1,"syntology":null},{"paper":"/paper/end-to-end-training-of-neural-retrievers-for","slug":"end-to-end-training-of-neural-retrievers-for","title":"End-to-End Training of Neural Retrievers for Open-Domain Question Answering","date":"2021-01-02","arxiv_id":"2101.00408","n_code_links":2,"syntology":null},{"paper":"/paper/km-bart-knowledge-enhanced-multimodal-bart","slug":"km-bart-knowledge-enhanced-multimodal-bart","title":"KM-BART: Knowledge Enhanced Multimodal BART for Visual Commonsense Generation","date":"2021-01-02","arxiv_id":"2101.00419","n_code_links":1,"syntology":null},{"paper":null,"slug":"lex-bert-enhancing-bert-based-ner-with","title":"Lex-BERT: Enhancing BERT based NER with lexicons","date":"2021-01-02","arxiv_id":"2101.00396","n_code_links":0,"syntology":null},{"paper":"/paper/superbizarre-is-not-superb-improving-bert-s","slug":"superbizarre-is-not-superb-improving-bert-s","title":"Superbizarre Is Not Superb: Derivational Morphology Improves BERT's Interpretation of Complex Words","date":"2021-01-02","arxiv_id":"2101.00403","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 2 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["valentinhofmann/superbizarre"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"what-all-do-audio-transformer-models-hear","title":"What all do audio transformer models hear? Probing Acoustic Representations for Language Delivery and its Structure","date":"2021-01-02","arxiv_id":"2101.00387","n_code_links":0,"syntology":null},{"paper":"/paper/zero-shot-learning-by-generating-task","slug":"zero-shot-learning-by-generating-task","title":"Learning to Generate Task-Specific Adapters from Task Description","date":"2021-01-02","arxiv_id":"2101.00420","n_code_links":1,"syntology":null},{"paper":"/paper/a-geometric-analysis-of-deep-generative-image","slug":"a-geometric-analysis-of-deep-generative-image","title":"A Geometric Analysis of Deep Generative Image Models and Its Applications","date":"2021-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"a-new-variant-of-stochastic-heavy-ball","title":"A New Variant of Stochastic Heavy ball Optimization Method for Deep Learning","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"adam-revisited-a-weighted-past-gradients","title":"Adam revisited: a weighted past gradients perspective","date":"2021-01-01","arxiv_id":"2101.00238","n_code_links":0,"syntology":null},{"paper":null,"slug":"adding-recurrence-to-pretrained-transformers-1","title":"Adding Recurrence to Pretrained Transformers","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"analogical-reasoning-for-visually-grounded-1","title":"Analogical Reasoning for Visually Grounded Compositional Generalization","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"apollo-an-adaptive-parameter-wised-diagonal","title":"Apollo: An Adaptive Parameter-wised Diagonal Quasi-Newton Method for Nonconvex Stochastic Optimization","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"ariel-volume-coding-for-sentence-generation-1","title":"AriEL: Volume Coding for Sentence Generation Comparisons","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-is-not-enough-mitigating-the","title":"Attention Is Not Enough: Mitigating the Distribution Discrepancy in Asynchronous Multimodal Sequence Fusion","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"block-skim-transformer-for-efficient-question","title":"Block Skim Transformer for Efficient Question Answering","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"bros-a-pre-trained-language-model-for","title":"BROS: A Pre-trained Language Model for Understanding Texts in Document","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cluster-former-clustering-based-sparse-1","title":"Cluster-Former: Clustering-based Sparse Transformer for Question Answering","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cluster-tune-enhance-bert-performance-in-low","title":"Cluster & Tune: Enhance BERT Performance in Low Resource Text Classification","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"convergent-adaptive-gradient-methods-in","title":"Convergent Adaptive Gradient Methods in Decentralized Optimization","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/crackformer-transformer-network-for-fine","slug":"crackformer-transformer-network-for-fine","title":"CrackFormer: Transformer Network for Fine-Grained Crack Detection","date":"2021-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"cross-probe-bert-for-efficient-and-effective","title":"Cross-Probe BERT for Efficient and Effective Cross-Modal Search","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"dact-bert-increasing-the-efficiency-and","title":"DACT-BERT: Increasing the efficiency and interpretability of BERT by using adaptive computation time.","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"data-aware-low-rank-compression-for-large-nlp","title":"Data-aware Low-Rank Compression for Large NLP Models","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-proteins-using-a-triplet-bert","title":"Deep Learning Proteins using a Triplet-BERT network","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/deep-representational-re-tuning-using","slug":"deep-representational-re-tuning-using","title":"Deep Representational Re-tuning using Contrastive Tension","date":"2021-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"discovering-human-interactions-with-large","title":"Discovering Human Interactions With Large-Vocabulary Objects via Query and Multi-Scale Detection","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"do-transformers-understand-polynomial","title":"Do Transformers Understand Polynomial Simplification?","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"domain-slot-relationship-modeling-using-a-pre","title":"Domain-slot Relationship Modeling using a Pre-trained Language Encoder for Multi-Domain Dialogue State Tracking","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"dynamic-detr-end-to-end-object-detection-with","title":"Dynamic DETR: End-to-End Object Detection With Dynamic Attention","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"erasure-for-advancing-dynamic-self-supervised","title":"Erasure for Advancing: Dynamic Self-Supervised Learning for Commonsense Reasoning","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/event-based-video-reconstruction-using","slug":"event-based-video-reconstruction-using","title":"Event-Based Video Reconstruction Using Transformer","date":"2021-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-routing-strategies-for-multilingual","title":"Exploring Routing Strategies for Multilingual Mixture-of-Experts Models","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-vulnerabilities-of-bert-based-apis","title":"EXPLORING VULNERABILITIES OF BERT-BASED APIS","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"factored-action-spaces-in-deep-reinforcement","title":"Factored Action Spaces in Deep Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"frequency-aware-spatiotemporal-transformers","title":"Frequency-Aware Spatiotemporal Transformers for Video Inpainting Detection","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"generalizing-tree-models-for-improving","title":"Generalizing Tree Models for Improving Prediction Accuracy","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"high-performance-discriminative-tracking-with","title":"High-Performance Discriminative Tracking With Transformers","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"how-multipurpose-are-language-models","title":"How Multipurpose Are Language Models?","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"hypergrid-transformers-towards-a-single-model","title":"HyperGrid Transformers: Towards A Single Model for Multiple Tasks","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/image-harmonization-with-transformer","slug":"image-harmonization-with-transformer","title":"Image Harmonization With Transformer","date":"2021-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-generalizability-of-protein","title":"Improving Generalizability of Protein Sequence Models via Data Augmentations","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-machine-translation-by-searching","title":"Improving Machine Translation by Searching Skip Connections Efficiently","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"isotropy-in-the-contextual-embedding-space","title":"Isotropy in the Contextual Embedding Space: Clusters and Manifolds","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null}],"record_sha256":"2f0e8403a8e949d7a22c31f24c13c1ff1da7ae4caed566b399c54ff7c28b50aa","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}